Hugging Face's logo

FKTech
/
DPR_QUERY_and_DOC_ENCODER

Safetensors
Model card Files
xet
Community
FKTech commited on
Commit
e49c3d4
·
verified ·
1 Parent(s): c558d8a

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. passage_encoder/config.json +1 -1
  2. passage_encoder/model.safetensors +1 -1
  3. passage_tokenizer/special_tokens_map.json +7 -0
  4. passage_tokenizer/tokenizer_config.json +58 -0
  5. passage_tokenizer/vocab.txt +0 -0
  6. query_encoder/config.json +1 -1
  7. query_encoder/model.safetensors +1 -1
  8. query_tokenizer/special_tokens_map.json +7 -0
  9. query_tokenizer/tokenizer_config.json +58 -0
  10. query_tokenizer/vocab.txt +0 -0
passage_encoder/config.json CHANGED
@@ -19,7 +19,7 @@
19
  "position_embedding_type": "absolute",
20
  "projection_dim": 0,
21
  "torch_dtype": "float32",
22
- "transformers_version": "4.47.1",
23
  "type_vocab_size": 2,
24
  "vocab_size": 30522
25
  }
 
19
  "position_embedding_type": "absolute",
20
  "projection_dim": 0,
21
  "torch_dtype": "float32",
22
+ "transformers_version": "4.48.2",
23
  "type_vocab_size": 2,
24
  "vocab_size": 30522
25
  }
passage_encoder/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:644fc976add3d7a7a5617c214cef21fb25d596c4e6d13cf59eeca499539cb77a
3
  size 435593312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69eb651c689e75a8c85ee73ffd5fcdc290e6b387cee7716c6994fc9103c889e0
3
  size 435593312
passage_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
passage_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "DPRContextEncoderTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
passage_tokenizer/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
query_encoder/config.json CHANGED
@@ -19,7 +19,7 @@
19
  "position_embedding_type": "absolute",
20
  "projection_dim": 0,
21
  "torch_dtype": "float32",
22
- "transformers_version": "4.47.1",
23
  "type_vocab_size": 2,
24
  "vocab_size": 30522
25
  }
 
19
  "position_embedding_type": "absolute",
20
  "projection_dim": 0,
21
  "torch_dtype": "float32",
22
+ "transformers_version": "4.48.2",
23
  "type_vocab_size": 2,
24
  "vocab_size": 30522
25
  }
query_encoder/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b39a1527749f21cd97342ec2d1024f58c39f3e07d8a24bcc11b2e176e0713405
3
  size 435594296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17dfe21dfd0ab96ceca11af77e64dc382aa194ac3caa3cdb1b7be2a396e4bf9
3
  size 435594296
query_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
query_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "DPRQuestionEncoderTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
query_tokenizer/vocab.txt ADDED
The diff for this file is too large to render. See raw diff